TY - JOUR

T1 - Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail

AU - Punia, Sushil

AU - Nikolopoulos, Kostas

AU - Prakash Singh, Surya

AU - Madaan, Jitendra K.

AU - Litsiou, Konstantina

PY - 2020/8/17

Y1 - 2020/8/17

N2 - This paper proposes a novel forecasting method that combines the deep learning method - long short-term memory (LSTM) networks and random forest (RF). The proposed method can model complex relationships of both temporal and regression type which gives it an edge in accuracy over other forecasting methods. We evaluated the new method on a real-world multivariate dataset from a multi-channel retailer. We benchmark the forecasting performance of the new proposition against neural networks, multiple regression, ARIMAX, LSTM networks, and RF. We employed forecasting performance metrics to measure bias, accuracy, and variance, and the empirical evidence suggests that the new proposition is (statistically) significantly better. Furthermore, our method ranks the explanatory variables in terms of their relative importance. The empirical evaluations are replicated for longer forecasting horizons, and online and offline channels and the same conclusions hold; thus, advocating for the robustness of our forecasting proposition as well as the suitability in multi-channel retail demand forecasting.

AB - This paper proposes a novel forecasting method that combines the deep learning method - long short-term memory (LSTM) networks and random forest (RF). The proposed method can model complex relationships of both temporal and regression type which gives it an edge in accuracy over other forecasting methods. We evaluated the new method on a real-world multivariate dataset from a multi-channel retailer. We benchmark the forecasting performance of the new proposition against neural networks, multiple regression, ARIMAX, LSTM networks, and RF. We employed forecasting performance metrics to measure bias, accuracy, and variance, and the empirical evidence suggests that the new proposition is (statistically) significantly better. Furthermore, our method ranks the explanatory variables in terms of their relative importance. The empirical evaluations are replicated for longer forecasting horizons, and online and offline channels and the same conclusions hold; thus, advocating for the robustness of our forecasting proposition as well as the suitability in multi-channel retail demand forecasting.

KW - LSTM networks

KW - deep learning

KW - multi-channel

KW - random forests

KW - retail

U2 - 10.1080/00207543.2020.1735666

DO - 10.1080/00207543.2020.1735666

M3 - Article

VL - 58

SP - 4964

EP - 4979

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 16

ER -